© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 13914
    Prev
    Next
    INDEX
    Explanations

    the beginning/identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     mutual
    -0.11
    hes
    -0.10
     langu
    -0.10
    rieved
    -0.10
     ours
    -0.10
     intimacy
    -0.10
    apsed
    -0.09
    our
    -0.09
     fraught
    -0.08
     spender
    -0.08
    POSITIVE LOGITS
     pain
    0.21
     Pain
    0.16
    pain
    0.16
     sensations
    0.14
     painful
    0.14
     pains
    0.14
     ache
    0.14
     humiliation
    0.13
     humiliating
    0.13
     headache
    0.13
    Activations Density 0.028%

    No Known Activations